メニュー
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
AI-powered Draw.io diagram generation with real-time browser preview. Create flowcharts, architecture diagrams, sequence diagrams, and cloud infrastructure diagrams (AWS/GCP/Azure) using natural language. Supports animated connectors, real-time editing, and structured A–H format extraction from text or images.
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this,"...
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
| name | auto-research |
| description | Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval. |
| category | automation |
| risk | critical |
| source | self |
| source_type | self |
| date_added | 2026-07-09 |
| author | zyu51 |
| tags | ["research","chatgpt","playwright","browser-automation","decision-support","chinese"] |
| tools | ["claude","playwright"] |
| license | MIT |
When implementing tasks, Claude Code can encounter uncertainties — design choices, algorithm details, API usage, or best practices. This skill provides an explicit-consent research path, presents findings, and waits for user approval before writing code.
The skill supports web research and an optional ChatGPT consultation. It never sends conversation context, files, browser state, or credentials to a third party without the user's explicit approval of the exact, redacted text.
Step 1: Propose the research boundary — State the source to use, the exact query or redacted prompt, whether any local/workspace text would leave the machine, and the likely cost. Wait for the user to approve that exact boundary.
Step 2: Research — After approval, use web search or a browser session the user has
explicitly selected and authorized. Use a pinned, user-configured browser automation
connector; do not install packages automatically, use @latest, or access browser cookies,
other tabs, saved passwords, or sessions.
Step 3: Present — Distill findings into concise options with sources, presented to the user.
Step 4: Await Approval — Do NOT write code until the user says "go ahead" or picks an option.
Step 5: Implement — Once approved, execute with confidence.
Do not treat ?, ??, or another shorthand as consent. First propose a minimal prompt,
for example: 请评估这个已脱敏的方案的正确性、完整性和可改进之处：<text>.
Explicitly identify every piece of text that would be sent. Only after the user confirms
the exact prompt may you open the selected ChatGPT session, submit that prompt, and present
the response. Do not include conversation history by default.
Redact secrets, personal data, proprietary code, customer data, and internal URLs before proposing the prompt. If safe redaction is not possible, do not submit it.
If browser automation is necessary, the user must separately authorize the selected browser profile and connector version. Restrict the session to the consultation tab. Do not inspect, reuse, export, or rely on cookies from other tabs or profiles.
User: PyTorch 中自定义 ADMM 优化器怎么设计？
Claude: 我可以搜索公开资料，或将以下已脱敏问题发给 ChatGPT：
“如何设计 PyTorch 自定义 ADMM 优化器？请比较可行模式。”
不会发送工作区文件或对话历史。是否允许？
User: 允许发送这段文字
Claude: [Opens only the authorized consultation tab, submits the approved prompt]
Claude: GPT suggests approach A with these pros/cons. Proceed?
User: 行
Claude: [Implements code]
User: ?? ADMM convergence criteria best practices
Claude: [WebSearch + WebFetch → finds Boyd et al. paper, extracts criteria]
Claude: Boyd recommends ||r|| < ε·max(||Ax||, ||Bz||, ||c||). Use this?
User: Yes
Claude: [Implements]
page.fill() for instant text injection instead of keyboard.type()| Problem | Solution |
|---|---|
| ChatGPT shows login page | Let the user log in themselves; do not handle cookies or credentials |
| The prompt contains sensitive context | Redact it or use local reasoning instead |
| Browser automation is unavailable | Use web search or stop and ask the user for a different approved method |